The Normal distribution

The Normal distribution

Spec N2 · AQA A-Level Maths: Revision notes

Studying this course? Keep your progress in one place.

Key facts

  • X∼N(μ,σ2)X\sim N(\mu,\sigma^2): a symmetrical bell shape centred on the mean μ\mu; σ2\sigma^2 is the variance.
  • Standardise with Z=X−μσ∼N(0,1)Z=\frac{X-\mu}{\sigma}\sim N(0,1).
  • Inverse problems: x=μ+zσx=\mu+z\sigma; P<0.5P<0.5 gives a negative zz.
  • About 68%68\%, 95%95\% and 99.7%99.7\% of values lie within 11, 22 and 33 standard deviations; inflection points are at μ±σ\mu\pm\sigma.
  • B(n,p)≈N(np,np(1−p))B(n,p)\approx N\big(np,np(1-p)\big) with a continuity correction.

The Normal model

It models a continuous quantity that clusters around a central value and tails off symmetrically.

The Normal distribution models a continuous quantity, such as a mass or a time, whose values cluster around a central value. We write X∼N(μ,σ2)X\sim N(\mu,\sigma^2), where μ\mu is the mean and σ2\sigma^2 the variance, so the standard deviation is σ\sigma.

The probability density function is a symmetrical bell shape with its maximum at x=μx=\mu, so the mean, median and mode are equal. The total area is 11, and for a continuous variable P(X=x)=0P(X=x)=0. Sketch and shade the region you want before using the calculator.

455055606570750.020.040.060.080.1xyx = μ = 60N(60, 4²)
The density of N(60,42)N(60,4^2): symmetrical about x=60x=60, with total area 11.

X∼N(50,9)X\sim N(50,9). What is the standard deviation?

Finding probabilities

Use the calculator with μ\mu and σ\sigma, or standardise and use the standard Normal table.

Use the Normal cumulative distribution function on your calculator with the correct μ\mu and σ\sigma (not σ2\sigma^2). Without it, standardise: Z=X−μσ∼N(0,1)Z=\frac{X-\mu}{\sigma}\sim N(0,1), the standard Normal distribution.

The curve is symmetrical, so P(Z>a)=1−P(Z<a)P(Z>a)=1-P(Z<a) and P(Z<−a)=1−P(Z<a)P(Z<-a)=1-P(Z<a).

455055606570750.020.040.060.080.1xyx = 64N(60, 4²)
P(X>64)P(X>64) for X∼N(60,42)X\sim N(60,4^2) is the shaded area, P(Z>1)P(Z>1).
  • StandardiseZ=X−μσZ=\dfrac{X-\mu}{\sigma}

Worked example

X∼N(60,42)X\sim N(60,4^2). Find P(X>64)P(X>64) and P(56<X<63)P(56<X<63).

Z∼N(0,1)Z\sim N(0,1) and P(Z<1.2)=0.8849P(Z<1.2)=0.8849. What is P(Z>1.2)P(Z>1.2)?

Inverse problems

Find zz for the probability, then x=μ+zσx=\mu+z\sigma; unknown parameters give simultaneous equations.

To find xx given a probability, use the inverse Normal function. If P(X<x)=pP(X<x)=p, then x=μ+zσx=\mu+z\sigma where P(Z<z)=pP(Z<z)=p. A cumulative probability below 0.50.5 gives a negative zz.

When μ\mu or σ\sigma is unknown, standardise each given probability to get an equation. Two conditions give two simultaneous equations.

−4−3−2−112340.10.20.30.4xyz = 1.2816N(0, 1²)
Inverse Normal: the shaded area P(Z < z) = 0.9 is given, and the inverse Normal function returns z = 1.2816.
  • P(X<x)=pP(X<x)=px=μ+zσx=\mu+z\sigma

Worked example

T∼N(25,62)T\sim N(25,6^2) and 90%90\% of times are below tt. Find tt.

Worked example

Y∼N(μ,σ2)Y\sim N(\mu,\sigma^2) with P(Y<30)=0.2P(Y<30)=0.2 and P(Y>45)=0.1P(Y>45)=0.1. Find μ\mu and σ\sigma.

P(X<x)=0.3P(X<x)=0.3 for a Normal distribution. The zz-value is…

Shape and spread

μ\mu sets the position and σ\sigma the width; inflection points are at μ±σ\mu\pm\sigma.

μ\mu fixes the position of the curve and σ\sigma its width. A larger σ\sigma gives a wider, flatter curve, because the total area stays 11.

The curve has points of inflection at x=μ±σx=\mu\pm\sigma; for N(60,42)N(60,4^2) these are at 5656 and 6464. Approximately 68%68\% of values lie within 1σ1\sigma of the mean, 95%95\% within 2σ2\sigma and 99.7%99.7\% within 3σ3\sigma. With the same mean, the distribution with the smaller σ\sigma is more consistent.

4045505560657075800.020.040.060.080.10.120.140.160.180.2xyN(60, s²)
Drag ss: the curve flattens as σ\sigma grows (inflection at μ±σ\mu\pm\sigma).
0204060801001σ2σ3σDistance from meanPercentage of values (%)
Approximate percentage of values within k standard deviations of the mean.

X∼N(100,52)X\sim N(100,5^2). Where are the points of inflection?

Try an exam question

X∼N(72,62)X\sim N(72,6^2). Find P(X>81)P(X>81), and find the value xx such that P(X<x)=0.9P(X<x)=0.9.

[4 marks]

That's the notes covered.

Carry on to the next subtopic.

Try a question

Find the probability that an egg has a mass greater than 6464 g.

1 mark, marked against the mark scheme

Revision notes